SCSimulator: An Exploratory Visual Analytics Framework for Partner Selection in Supply Chains through LLM-driven Multi-Agent Simulation

2026-01-21

AI Summary

This study addresses the challenge of supplier selection in supply chains, which is shaped by complex coopetitive relationships and multi-objective dynamic games, rendering traditional methods inadequate due to their inability to capture real-world complexity and susceptibility to subjective bias. To overcome these limitations, this work proposes a novel framework integrating large language model (LLM)-driven multi-agent simulation with human-in-the-loop visual analytics. The approach leverages adaptive network structures and chain-of-thought (CoT) reasoning to simulate firm behaviors and supply chain evolution, while incorporating explainable AI (XAI) to enable interactive user exploration and intervention. This research represents the first integration of LLM-based multi-agent systems, XAI, and expert-informed decision-making, with scenario-based validation and user studies demonstrating significant improvements in transparency, flexibility, and practical utility for partner selection.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Multiagent Systems: Mechanism Design
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Supply chains (SCs), complex networks spanning from raw material acquisition to product delivery, with enterprises as interconnected nodes, play a pivotal role in organizational success. However, optimizing SCs remains challenging, particularly in partner selection, a key bottleneck shaped by competitive and cooperative dynamics. This challenge constitutes a multi-objective dynamic game requiring a synergistic integration of Multi-Criteria Decision-Making and Game Theory. Traditional approaches, grounded in mathematical simplifications and managerial heuristics, fail to capture real-world intricacies and risk introducing subjective biases. Multi-agent simulation offers promise, but prior research has largely relied on fixed, uniform agent logic, limiting practical applicability. Recent advances in LLMs create opportunities to represent complex SC requirements and hybrid game logic. However, challenges persist in modeling dynamic SC relationships, ensuring interpretability, and balancing agent autonomy with expert control. We present SCSimulator, a visual analytics framework that integrates LLM-driven MAS with human-in-the-loop collaboration for SC partner selection. It simulates SC evolution via adaptive network structures and enterprise behaviors, which are visualized via interpretable interfaces. By combining CoT reasoning with XAI techniques, it generates multi-faceted, transparent explanations of decision trade-offs. Users can iteratively adjust simulation settings to explore outcomes aligned with their expectations and strategic priorities. Developed through iterative co-design with SC experts and industry managers, SCSimulator serves as a proof-of-concept, offering methodological contributions and practical insights for future research on SC decision-making and interactive AI-driven analytics. Usage scenarios and a user study demonstrate the system's effectiveness and usability.

Problem

• partner selection
• supply chain
• multi-agent simulation
• LLM-driven
• visual analytics

Innovation

• LLM-driven multi-agent simulation
• visual analytics
• human-in-the-loop
• explainable AI (XAI)
• supply chain partner selection